Performance question
If your VM system is at 101% memory usage, and you are overcommitted by about 14%, is it worthwhile to add a vdisk to a linux for swap space, or better just to add main memory to the linux? MA (Looking for opinions, thoughts, rationalizations, whatever. :)
Re: Performance question
My SLES 10.1 zLinux servers have been notorious for not making much use of the swap space, even when we lower the main (virtualized) in the USER DIRECTORY. We may have something just not configured optimally somewhere, but our luck has gone with adding main Linux memory and subsequently having to add ZVM memory. David Dean Information Systems *bcbstauthorized* From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Mary Anne Matyaz Sent: Monday, September 29, 2008 11:31 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Performance question If your VM system is at 101% memory usage, and you are overcommitted by about 14%, is it worthwhile to add a vdisk to a linux for swap space, or better just to add main memory to the linux? MA (Looking for opinions, thoughts, rationalizations, whatever. :) Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm
Re: Performance question
Best practices is to use Vdisk for swap, and reduce linux virtual machine sizes - not to buy more REAL z/VM memory unless you really need it. 101% memory useage means almost nothing. It is not relevant to performance or capacity, and thus shouldn't have business decisions or performance decisions decided based on that number. Dean, David (I/S) wrote: My SLES 10.1 zLinux servers have been notorious for not making much use of the swap space, even when we lower the main (virtualized) in the USER DIRECTORY. We may have something just not configured optimally somewhere, but our luck has gone with adding main Linux memory and subsequently having to add ZVM memory. David Dean Information Systems *bcbstauthorized* From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Mary Anne Matyaz Sent: Monday, September 29, 2008 11:31 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Performance question If your VM system is at 101% memory usage, and you are overcommitted by about 14%, is it worthwhile to add a vdisk to a linux for swap space, or better just to add main memory to the linux? MA (Looking for opinions, thoughts, rationalizations, whatever. :) Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm
Re: Performance question
Can you give me any insight into making more use of the swap; see below? We have had systems significantly speed up after adding memory, even though swap was not being used. I realize that swap / disk is going to be slower, but with cache and buffers shouldn't it be at least close? lnx057:~ # free -l total used free sharedbuffers cached Mem:763208 758572 4636 0 77092 592676 Low:763208 758572 4636 High:0 0 0 -/+ buffers/cache: 88804 674404 Swap: 10798963001079596 Thank you for any help. David Dean Information Systems *bcbstauthorized* -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Barton Robinson Sent: Monday, September 29, 2008 1:23 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance question Best practices is to use Vdisk for swap, and reduce linux virtual machine sizes - not to buy more REAL z/VM memory unless you really need it. 101% memory useage means almost nothing. It is not relevant to performance or capacity, and thus shouldn't have business decisions or performance decisions decided based on that number. Dean, David (I/S) wrote: My SLES 10.1 zLinux servers have been notorious for not making much use of the swap space, even when we lower the main (virtualized) in the USER DIRECTORY. We may have something just not configured optimally somewhere, but our luck has gone with adding main Linux memory and subsequently having to add ZVM memory. David Dean Information Systems *bcbstauthorized* From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Mary Anne Matyaz Sent: Monday, September 29, 2008 11:31 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Performance question If your VM system is at 101% memory usage, and you are overcommitted by about 14%, is it worthwhile to add a vdisk to a linux for swap space, or better just to add main memory to the linux? MA (Looking for opinions, thoughts, rationalizations, whatever. :) Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm
Re: Performance question
I know I'm probably going to regret this, but, how can that be? I said VM memory usage, right? Not Linux MA On Mon, Sep 29, 2008 at 1:23 PM, Barton Robinson [EMAIL PROTECTED] wrote: Best practices is to use Vdisk for swap, and reduce linux virtual machine sizes - not to buy more REAL z/VM memory unless you really need it. 101% memory useage means almost nothing. It is not relevant to performance or capacity, and thus shouldn't have business decisions or performance decisions decided based on that number.
Re: Performance question
It appears there's alot of cache usage. What's running on this machine? -- Rich Smrcina VM Assist, Inc. Phone: 414-491-6001 Ans Service: 360-715-2467 rich.smrcina at vmassist.com http://www.linkedin.com/in/richsmrcina Catch the WAVV! http://www.wavv.org WAVV 2009 - Orlando, FL - May 15-19, 2009 Dean, David (I/S) wrote: Can you give me any insight into making more use of the swap; see below? We have had systems significantly speed up after adding memory, even though swap was not being used. I realize that swap / disk is going to be slower, but with cache and buffers shouldn't it be at least close? lnx057:~ # free -l total used free sharedbuffers cached Mem:763208 758572 4636 0 77092 592676 Low:763208 758572 4636 High:0 0 0 -/+ buffers/cache: 88804 674404 Swap: 10798963001079596 Thank you for any help. David Dean Information Systems *bcbstauthorized* -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Barton Robinson Sent: Monday, September 29, 2008 1:23 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance question Best practices is to use Vdisk for swap, and reduce linux virtual machine sizes - not to buy more REAL z/VM memory unless you really need it. 101% memory useage means almost nothing. It is not relevant to performance or capacity, and thus shouldn't have business decisions or performance decisions decided based on that number. Dean, David (I/S) wrote: My SLES 10.1 zLinux servers have been notorious for not making much use of the swap space, even when we lower the main (virtualized) in the USER DIRECTORY. We may have something just not configured optimally somewhere, but our luck has gone with adding main Linux memory and subsequently having to add ZVM memory. David Dean Information Systems *bcbstauthorized* From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Mary Anne Matyaz Sent: Monday, September 29, 2008 11:31 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Performance question If your VM system is at 101% memory usage, and you are overcommitted by about 14%, is it worthwhile to add a vdisk to a linux for swap space, or better just to add main memory to the linux? MA (Looking for opinions, thoughts, rationalizations, whatever. :) Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm
Re: Performance question
It is predominately a file server +600GIG. The OS is SUSE 10.1 (Novell). David Dean Information Systems *bcbstauthorized* -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Rich Smrcina Sent: Monday, September 29, 2008 12:46 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance question It appears there's alot of cache usage. What's running on this machine? -- Rich Smrcina VM Assist, Inc. Phone: 414-491-6001 Ans Service: 360-715-2467 rich.smrcina at vmassist.com http://www.linkedin.com/in/richsmrcina Catch the WAVV! http://www.wavv.org WAVV 2009 - Orlando, FL - May 15-19, 2009 Dean, David (I/S) wrote: Can you give me any insight into making more use of the swap; see below? We have had systems significantly speed up after adding memory, even though swap was not being used. I realize that swap / disk is going to be slower, but with cache and buffers shouldn't it be at least close? lnx057:~ # free -l total used free sharedbuffers cached Mem:763208 758572 4636 0 77092 592676 Low:763208 758572 4636 High:0 0 0 -/+ buffers/cache: 88804 674404 Swap: 10798963001079596 Thank you for any help. David Dean Information Systems *bcbstauthorized* -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Barton Robinson Sent: Monday, September 29, 2008 1:23 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance question Best practices is to use Vdisk for swap, and reduce linux virtual machine sizes - not to buy more REAL z/VM memory unless you really need it. 101% memory useage means almost nothing. It is not relevant to performance or capacity, and thus shouldn't have business decisions or performance decisions decided based on that number. Dean, David (I/S) wrote: My SLES 10.1 zLinux servers have been notorious for not making much use of the swap space, even when we lower the main (virtualized) in the USER DIRECTORY. We may have something just not configured optimally somewhere, but our luck has gone with adding main Linux memory and subsequently having to add ZVM memory. David Dean Information Systems *bcbstauthorized* From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Mary Anne Matyaz Sent: Monday, September 29, 2008 11:31 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Performance question If your VM system is at 101% memory usage, and you are overcommitted by about 14%, is it worthwhile to add a vdisk to a linux for swap space, or better just to add main memory to the linux? MA (Looking for opinions, thoughts, rationalizations, whatever. :) Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm
Re: Performance question
Dean, David (I/S) wrote: My SLES 10.1 zLinux servers have been notorious for not making much use of the swap space, even when we lower the main (virtualized) in the USER DIRECTORY. Linux uses extra memory for file cache buffers. When the kernel detects memory is short, it just allocates less of them and spends more time accessing the disk. Linux thinks it is its own virtual memory manager. It does not, one imagines, co-operate optimally w/r/t VM. -- Jack J. Woehr# Self-delusion is http://www.well.com/~jax # half the battle! http://www.softwoehr.com # - Zippy the Pinhead
Re: Performance question
Thanks to all for some really good input. So the tuning legend that the Linux should just touch swap is true? But if Linux is going to eat all for file caching, would it not Always eventually swap? Thanks again. Anything that is not a mystery is guesswork. David Dean Information Systems *bcbstauthorized* From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Jack Woehr Sent: Monday, September 29, 2008 12:55 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance question Dean, David (I/S) wrote: My SLES 10.1 zLinux servers have been notorious for not making much use of the swap space, even when we lower the main (virtualized) in the USER DIRECTORY. Linux uses extra memory for file cache buffers. When the kernel detects memory is short, it just allocates less of them and spends more time accessing the disk. Linux thinks it is its own virtual memory manager. It does not, one imagines, co-operate optimally w/r/t VM. -- Jack J. Woehr# Self-delusion is http://www.well.com/~jax # half the battle! http://www.softwoehr.com # - Zippy the Pinhead Please see the following link for the BlueCross BlueShield of Tennessee E-mail disclaimer: http://www.bcbst.com/email_disclaimer.shtm
Re: Performance question
Dean, David (I/S) wrote: Thanks to all for some really good input. So the tuning legend that the Linux should just touch swap is true? But if Linux is going to eat all for file caching, would it not Always eventually swap? Swap and file caching are two sides of the same thing. In Solaris, they are the same thing, not quite so in Linux. Basically, Linux will use extra mem for file caching. It will always use *some* mem for file caching. It will use less if mem is constrained. Linux kernel for running on VM could be designed a little different from Linux kernel for PC in order to behave better with VM. I'm not sure to what extent it actually is different. -- Jack J. Woehr# Self-delusion is http://www.well.com/~jax # half the battle! http://www.softwoehr.com # - Zippy the Pinhead
Re: Performance question
On Monday, 09/29/2008 at 01:41 EDT, Jack Woehr [EMAIL PROTECTED] wrote: Linux kernel for running on VM could be designed a little different from Linux kernel for PC in order to behave better with VM. I'm not sure to what extent it actually is different. This is not just a z/VM problem. For any virtualization platform that overcommits memory, Linux memory usage will be problematic. I hope that, someday, Linux will have a generalized ability to sense its surroundings and constrain itself according to the wishes of the hypervisor. I.e. learn whether or not it is sharing the CPU, memory, and I/O, and know the relative value of each. For example, knowing that on System z, I/O is not a Bad Thing as it is in Intel (this is what drives Linux' fanatical use of cache - I/O is evil) would lead to different biases in the cache management subsystem. That bias could be further influenced by communication between the hypervisor and Linux (similar to CMM on z/VM). Alan Altmark z/VM Development IBM Endicott
Re: Performance question
z/VM Memory usage, what do you think it means? If a page of a virtual machine is in storage, but has not been referenced in 10 minutes, is that part of your percent used? Likely you don't know the answer and the source of your information doesn't either. So if that's the case, what information are you using to make decisions? Mary Anne Matyaz wrote: I know I'm probably going to regret this, but, how can that be? I said VM memory usage, right? Not Linux MA On Mon, Sep 29, 2008 at 1:23 PM, Barton Robinson [EMAIL PROTECTED] wrote: Best practices is to use Vdisk for swap, and reduce linux virtual machine sizes - not to buy more REAL z/VM memory unless you really need it. 101% memory useage means almost nothing. It is not relevant to performance or capacity, and thus shouldn't have business decisions or performance decisions decided based on that number.
Re: Performance question
If the page has not been referenced in 10 minutes, but is not paged out, I would expect it to be included in the 101%. Try not to focus so much on the extraneous info and address the question, if I am using a huge amount of memory, is it more helpful to use vdisk or guest memory? MA On Mon, Sep 29, 2008 at 3:32 PM, Barton Robinson [EMAIL PROTECTED] wrote: z/VM Memory usage, what do you think it means? If a page of a virtual machine is in storage, but has not been referenced in 10 minutes, is that part of your percent used? Likely you don't know the answer and the source of your information doesn't either. So if that's the case, what information are you using to make decisions? Mary Anne Matyaz wrote: I know I'm probably going to regret this, but, how can that be? I said VM memory usage, right? Not Linux MA On Mon, Sep 29, 2008 at 1:23 PM, Barton Robinson [EMAIL PROTECTED] wrote: Best practices is to use Vdisk for swap, and reduce linux virtual machine sizes - not to buy more REAL z/VM memory unless you really need it. 101% memory useage means almost nothing. It is not relevant to performance or capacity, and thus shouldn't have business decisions or performance decisions decided based on that number.
Re: Performance question
Alan Altmark wrote: On Monday, 09/29/2008 at 01:41 EDT, Jack Woehr [EMAIL PROTECTED] wrote: Linux kernel for running on VM could be designed a little different from Linux kernel for PC in order to behave better with VM. I'm not sure to what extent it actually is different. This is not just a z/VM problem. Didn't mean to imply it was. For any virtualization platform that overcommits memory, Linux memory usage will be problematic. I hope that, someday, Linux will have a generalized ability to sense its surroundings and constrain itself according to the wishes of the hypervisor. It may be more pratical to modify the kernel so that it implements some of its functionality directly in terms of what the hypervisor provides rather than by assuming it controls all memory. This is the dialectic of modern virtualization scheme ... VMWare is like z/VM, the guest knows nothing, vs. Xen, the guest is modified to support the hypervisor. The former is cleaner and more secure, the latter more efficient execution. -- Jack J. Woehr# Self-delusion is http://www.well.com/~jax # half the battle! http://www.softwoehr.com # - Zippy the Pinhead
Re: Performance question
Best practices is to use Vdisk for swap Mary Anne Matyaz wrote: If the page has not been referenced in 10 minutes, but is not paged out, I would expect it to be included in the 101%. Try not to focus so much on the extraneous info and address the question, if I am using a huge amount of memory, is it more helpful to use vdisk or guest memory? MA On Mon, Sep 29, 2008 at 3:32 PM, Barton Robinson [EMAIL PROTECTED] wrote: z/VM Memory usage, what do you think it means? If a page of a virtual machine is in storage, but has not been referenced in 10 minutes, is that part of your percent used? Likely you don't know the answer and the source of your information doesn't either. So if that's the case, what information are you using to make decisions? Mary Anne Matyaz wrote: I know I'm probably going to regret this, but, how can that be? I said VM memory usage, right? Not Linux MA On Mon, Sep 29, 2008 at 1:23 PM, Barton Robinson [EMAIL PROTECTED] wrote: Best practices is to use Vdisk for swap, and reduce linux virtual machine sizes - not to buy more REAL z/VM memory unless you really need it. 101% memory useage means almost nothing. It is not relevant to performance or capacity, and thus shouldn't have business decisions or performance decisions decided based on that number.
Re: Performance Question
I see messages like this from time to time on my VM Lpars that only run guest operating systems and have little to no CMS users. I think it may be because the VM scheduler can't really see what a transaction is inside the GOS. I think it may just be an artifact of VM having an earlier design point of support a lot of concurrent users that have a lot of think time, rather than a farm of GOSes. From: The IBM z/VM Operating System on behalf of Martin, Terry R. (CMS/CTR) (CTR) Sent: Wed 9/24/2008 10:54 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance Question The REAL processors are running about 85% per (5 IFLs) and the virtual processors for this Linux host are running an average of about 90% per (4 Logicals). There is no CPU queuing that I can tell. I am not running any of the products you mentioned. This may not be a bad indicator I am just trying to find out what it really means since the default shipped is 1.000 elapse time not sure if that means much! Thanks, Terry From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of David Kreuter Sent: Wednesday, September 24, 2008 9:03 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance Question hard to say for certain. Not a number I look at that often. How busy are the processors? Is there CPU queuing? The scheduler tries to classify around 80% of work as class 1; so fluctuations are rather common. Are you per chance running WebSphere, WPS or Domino servers? David Kreuter From: The IBM z/VM Operating System on behalf of Martin, Terry R. (CMS/CTR) (CTR) Sent: Wed 9/24/2008 3:42 PM To: IBMVM@LISTSERV.UARK.EDU Subject: [IBMVM] Performance Question Hi I am trying to get a handle on all of the z/VM tuning knobs if you will and have a couple of questions: I see the following during heavy processing on the particular Linux host: FCXPER315A Cl1 time slice 8.939 exceeds limit 1.000 (Q1=02 Qx=26) I am using the default alert of 1.000 that is set in the PTK hence the alert. My question, is the fact that elapsed time which a class 1 user can spend in the dispatch list being 8.939 a high number and what is it really telling me? Does it represent a potential bottle neck? Thank You, Terry Martin Lockheed Martin - Information Technology z/OS z/VM Systems - Performance and Tuning Cell - 443 632-4191 Work - 410 786-0386 [EMAIL PROTECTED]
Re: Performance Question
Hi I know there are some performance folks out there (Velocity, IBM (Omegamon)) any thoughts on this from you all? Thanks Terry -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Quay, Jonathan (IHG) Sent: Thursday, September 25, 2008 7:19 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance Question I see messages like this from time to time on my VM Lpars that only run guest operating systems and have little to no CMS users. I think it may be because the VM scheduler can't really see what a transaction is inside the GOS. I think it may just be an artifact of VM having an earlier design point of support a lot of concurrent users that have a lot of think time, rather than a farm of GOSes. From: The IBM z/VM Operating System on behalf of Martin, Terry R. (CMS/CTR) (CTR) Sent: Wed 9/24/2008 10:54 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance Question The REAL processors are running about 85% per (5 IFLs) and the virtual processors for this Linux host are running an average of about 90% per (4 Logicals). There is no CPU queuing that I can tell. I am not running any of the products you mentioned. This may not be a bad indicator I am just trying to find out what it really means since the default shipped is 1.000 elapse time not sure if that means much! Thanks, Terry From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of David Kreuter Sent: Wednesday, September 24, 2008 9:03 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance Question hard to say for certain. Not a number I look at that often. How busy are the processors? Is there CPU queuing? The scheduler tries to classify around 80% of work as class 1; so fluctuations are rather common. Are you per chance running WebSphere, WPS or Domino servers? David Kreuter From: The IBM z/VM Operating System on behalf of Martin, Terry R. (CMS/CTR) (CTR) Sent: Wed 9/24/2008 3:42 PM To: IBMVM@LISTSERV.UARK.EDU Subject: [IBMVM] Performance Question Hi I am trying to get a handle on all of the z/VM tuning knobs if you will and have a couple of questions: I see the following during heavy processing on the particular Linux host: FCXPER315A Cl1 time slice 8.939 exceeds limit 1.000 (Q1=02 Qx=26) I am using the default alert of 1.000 that is set in the PTK hence the alert. My question, is the fact that elapsed time which a class 1 user can spend in the dispatch list being 8.939 a high number and what is it really telling me? Does it represent a potential bottle neck? Thank You, Terry Martin Lockheed Martin - Information Technology z/OS z/VM Systems - Performance and Tuning Cell - 443 632-4191 Work - 410 786-0386 [EMAIL PROTECTED]
Re: Performance Question
On Thu, Sep 25, 2008 at 2:04 PM, Martin, Terry R. (CMS/CTR) (CTR) [EMAIL PROTECTED] wrote: I know there are some performance folks out there (Velocity, IBM (Omegamon)) any thoughts on this from you all? The transaction as observed by CP relates to applications running in CMS. It has no meaning in the context of the transactions in the application running in Linux. However, when the virtual machine is using minimal CPU resources and CP still does not recognize transactions, you may conclude that the application is polling and thus hurting scalability (since memory management is based on dropping from queue when idle). Rob -- Rob van der Heij Velocity Software http://velocitysoftware.com/
Performance Question
Hi I am trying to get a handle on all of the z/VM tuning knobs if you will and have a couple of questions: I see the following during heavy processing on the particular Linux host: FCXPER315A Cl1 time slice 8.939 exceeds limit 1.000 (Q1=02 Qx=26) I am using the default alert of 1.000 that is set in the PTK hence the alert. My question, is the fact that elapsed time which a class 1 user can spend in the dispatch list being 8.939 a high number and what is it really telling me? Does it represent a potential bottle neck? Thank You, Terry Martin Lockheed Martin - Information Technology z/OS z/VM Systems - Performance and Tuning Cell - 443 632-4191 Work - 410 786-0386 [EMAIL PROTECTED]
Re: Performance Question
hard to say for certain. Not a number I look at that often. How busy are the processors? Is there CPU queuing? The scheduler tries to classify around 80% of work as class 1; so fluctuations are rather common. Are you per chance running WebSphere, WPS or Domino servers? David Kreuter From: The IBM z/VM Operating System on behalf of Martin, Terry R. (CMS/CTR) (CTR) Sent: Wed 9/24/2008 3:42 PM To: IBMVM@LISTSERV.UARK.EDU Subject: [IBMVM] Performance Question Hi I am trying to get a handle on all of the z/VM tuning knobs if you will and have a couple of questions: I see the following during heavy processing on the particular Linux host: FCXPER315A Cl1 time slice 8.939 exceeds limit 1.000 (Q1=02 Qx=26) I am using the default alert of 1.000 that is set in the PTK hence the alert. My question, is the fact that elapsed time which a class 1 user can spend in the dispatch list being 8.939 a high number and what is it really telling me? Does it represent a potential bottle neck? Thank You, Terry Martin Lockheed Martin - Information Technology z/OS z/VM Systems - Performance and Tuning Cell - 443 632-4191 Work - 410 786-0386 [EMAIL PROTECTED]
Re: Performance Question
The REAL processors are running about 85% per (5 IFLs) and the virtual processors for this Linux host are running an average of about 90% per (4 Logicals). There is no CPU queuing that I can tell. I am not running any of the products you mentioned. This may not be a bad indicator I am just trying to find out what it really means since the default shipped is 1.000 elapse time not sure if that means much! Thanks, Terry From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of David Kreuter Sent: Wednesday, September 24, 2008 9:03 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Performance Question hard to say for certain. Not a number I look at that often. How busy are the processors? Is there CPU queuing? The scheduler tries to classify around 80% of work as class 1; so fluctuations are rather common. Are you per chance running WebSphere, WPS or Domino servers? David Kreuter From: The IBM z/VM Operating System on behalf of Martin, Terry R. (CMS/CTR) (CTR) Sent: Wed 9/24/2008 3:42 PM To: IBMVM@LISTSERV.UARK.EDU Subject: [IBMVM] Performance Question Hi I am trying to get a handle on all of the z/VM tuning knobs if you will and have a couple of questions: I see the following during heavy processing on the particular Linux host: FCXPER315A Cl1 time slice 8.939 exceeds limit 1.000 (Q1=02 Qx=26) I am using the default alert of 1.000 that is set in the PTK hence the alert. My question, is the fact that elapsed time which a class 1 user can spend in the dispatch list being 8.939 a high number and what is it really telling me? Does it represent a potential bottle neck? Thank You, Terry Martin Lockheed Martin - Information Technology z/OS z/VM Systems - Performance and Tuning Cell - 443 632-4191 Work - 410 786-0386 [EMAIL PROTECTED]
Re: Rexx performance question
Gentlemen, You're comparing apples and bananas. EXECOMM and GLOBALV are two distinc t namespaces. Further, there is one GLOBALV set of variables, whereas each REXX invocation has its own set of variables (and then there is PROCEDURE EXPOSE). j.
Re: Rexx performance question
John, I think the original post required a comparison of unlike items. It was a question of, Is there a faster way to pass environment variables from one EXEC to another? The method in use was GLOBALV and the poster wanted to know if there was a more efficient, faster, way to do it. Regards, Richard Schuh -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of John P. Hartmann Sent: Thursday, January 18, 2007 8:24 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Rexx performance question Gentlemen, You're comparing apples and bananas. EXECOMM and GLOBALV are two distinc= t namespaces. Further, there is one GLOBALV set of variables, whereas each= REXX invocation has its own set of variables (and then there is PROCEDURE= EXPOSE). j.
Re: Rexx performance question
And, EXECCOMM must be used by GLOBALV GET and PUT. Hence there is some relation performance wise. -- Kris Buelens, IBM Belgium, VM customer support 2007/1/18, Schuh, Richard [EMAIL PROTECTED]: John, I think the original post required a comparison of unlike items. It was a question of, Is there a faster way to pass environment variables from one EXEC to another? The method in use was GLOBALV and the poster wanted to know if there was a more efficient, faster, way to do it. Regards, Richard Schuh -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of John P. Hartmann Sent: Thursday, January 18, 2007 8:24 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Rexx performance question Gentlemen, You're comparing apples and bananas. EXECOMM and GLOBALV are two distinc= t namespaces. Further, there is one GLOBALV set of variables, whereas each= REXX invocation has its own set of variables (and then there is PROCEDURE= EXPOSE). j.
Re: Rexx performance question
On 1/18/07, Kris Buelens [EMAIL PROTECTED] wrote: And, EXECCOMM must be used by GLOBALV GET and PUT. Hence there is some relation performance wise. Ooh... Sir Kris disagrees with the Piper... ;-)You have any old passwords I can inherit? Rob
Re: Rexx performance question
I've lots of things to inherit. But, even now after this dangerous adventure, I think I have some chances to survive. When I rethink my will, I'll think to leave something for you Sir Rob, Yours truly, Sir Kris The Guide, The proud owner of an almost uncountable -and still growing, number of preciously kept passwords. 2007/1/18, Rob van der Heij [EMAIL PROTECTED]: On 1/18/07, Kris Buelens [EMAIL PROTECTED] wrote: And, EXECCOMM must be used by GLOBALV GET and PUT. Hence there is some relation performance wise. Ooh... Sir Kris disagrees with the Piper... ;-)You have any old passwords I can inherit? Rob
Re: Rexx performance question
On 1/12/07, Peter Rothman [EMAIL PROTECTED] wrote: Besides a lot of 'steam lining' I thought I would be 'clever' and changed the GLOBALVs to 'PIPE var VarName 1 | var VarName'. The EXECCOMM interface is known to be slow. With GLOBALV you only use it once to set the variable, with the Pipeline you need 2 for the same thing. I would expect that to be slow. Depending on the number of Rexx variables present and involved, you may gain back some performance using 'rexxvars' to retrieve all variables and have a 'lookup' stage select the ones to use. If there's enough variables to copy that this makes a difference, then I assume they contain the data your subroutine works on. It is often not hard to make the subroutine in a pipe stage and pass the data through the pipeline rather than the Rexx variables. But the most efficient approach is of course to keep the data in the pipeline entirely. Rob
Re: Rexx performance question
The GLOBALV solution often also requires two calls to EXECCOMM: GLOBALV PUT in the calling exec and GLOBALV GET in the callee If the variables contain one word only, one can indeed save a call to EXECCOM: 'GLOBALV SET V1' content 'V2' content But, in such cases one can also pass the variables as arguments to the callee. In my PRFGUI package, this technique is extensively used. The caller: 'EXEC PRFGD PLOT' files ',', WorkWithTrd Spec407Bug UserVarsFnd NodeVarsFnd TracePipe chartid',', DtStringFromCharPtr DtStringToBuffer DtStringAppend DtObjectDelete, DtEventNotify DtValueSet DtValueGet DtTableCount DtTableQuery, hCnChanClo hCnChanRun hCnEdChMsg hCnEdChMsgC hCnLyChan',', Days2plot red cyan cyan2 yellow yellow2 gddmSticky, ',' hCnLsFlDisa, Note that I insert some separator character (a comma above) when a preceeding variable can be empty or when the contents can be more than 1 word. Needless to say that the corresponding PARSE ARG in the callee must have an indentical template. -- Kris Buelens, IBM Belgium, VM customer support 2007/1/13, Rob van der Heij [EMAIL PROTECTED]: On 1/12/07, Peter Rothman [EMAIL PROTECTED] wrote: Besides a lot of 'steam lining' I thought I would be 'clever' and changed the GLOBALVs to 'PIPE var VarName 1 | var VarName'. The EXECCOMM interface is known to be slow. With GLOBALV you only use it once to set the variable, with the Pipeline you need 2 for the same thing. I would expect that to be slow. Depending on the number of Rexx variables present and involved, you may gain back some performance using 'rexxvars' to retrieve all variables and have a 'lookup' stage select the ones to use. If there's enough variables to copy that this makes a difference, then I assume they contain the data your subroutine works on. It is often not hard to make the subroutine in a pipe stage and pass the data through the pipeline rather than the Rexx variables. But the most efficient approach is of course to keep the data in the pipeline entirely. Rob
Rexx performance question
We have an old REXX exec that I had to modify. This is a rather simplistic description but it consists of 2 parts - 1 to set up the environment(variables) and 2 to use the variables setup in 1. Bottom I had problems modifying it so I re-wrote it. The original used GLOBALV extensively - part 1 would do PUTs and part 2 would do GETs. Besides a lot of 'steam lining' I thought I would be 'clever' and changed the GLOBALVs to 'PIPE var VarName 1 | var VarName'. However the new exec ran much slower than the old. I then did a test to only compare GLOBALV PUT/GET to setting and retrieving the variable with PIPE var stage. The pipe stage was much slower. I thought the pipe logic would be better - obviously mistaken. Any comments - any other method I could have used that is perhaps faster than GLOBALV? Thanks Peter
Re: Rexx performance question
No, I had not. Thanks, I will try. Kris Buelens [EMAIL PROTECTED] il.comTo Sent by: The IBM IBMVM@LISTSERV.UARK.EDU z/VM Operating cc System [EMAIL PROTECTED] Subject ARK.EDU Re: Rexx performance question 01/12/2007 10:23 AM Please respond to The IBM z/VM Operating System [EMAIL PROTECTED] ARK.EDU Have you tried this too? PIPE LITERAL VAR1 VAR2 VAR3 ...| SPLIT |VARFETCH 1 DIRECT TOLOAD|VARLOAD DIRECT Note: the DIRECT tells not to try to resolve compound symbols, this also means one must pass the variable names in uppercase (and stem suffixes in the exact case). -- Kris Buelens, IBM Belgium, VM customer support 2007/1/12, Peter Rothman [EMAIL PROTECTED]: We have an old REXX exec that I had to modify. This is a rather simplistic description but it consists of 2 parts - 1 to set up the environment(variables) and 2 to use the variables setup in 1. Bottom I had problems modifying it so I re-wrote it. The original used GLOBALV extensively - part 1 would do PUTs and part 2 would do GETs. Besides a lot of 'steam lining' I thought I would be 'clever' and changed the GLOBALVs to 'PIPE var VarName 1 | var VarName'. However the new exec ran much slower than the old. I then did a test to only compare GLOBALV PUT/GET to setting and retrieving the variable with PIPE var stage. The pipe stage was much slower. I thought the pipe logic would be better - obviously mistaken. Any comments - any other method I could have used that is perhaps faster than GLOBALV? Thanks Peter
Re: Rexx performance question
From my testing, PIPES incur quite a bit of overhead when starting up. So, optimising means doing as much as possible within a PIPE to amortise that overhead over as much work as possible, and therefore using as few PIPE instances as possible. You could write the variables to a temporary disk file as well. But use EXECIO instead of PIPES to write the file, it uses less resources for small files. -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Peter Rothman Sent: January 12, 2007 10:55 To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Rexx performance question Tested that - also much slower than GLOBALV. Kris Buelens [EMAIL PROTECTED] il.com To Sent by: The IBM IBMVM@LISTSERV.UARK.EDU z/VM Operating cc System [EMAIL PROTECTED] Subject ARK.EDU Re: Rexx performance question 01/12/2007 10:23 AM Please respond to The IBM z/VM Operating System [EMAIL PROTECTED] ARK.EDU Have you tried this too? PIPE LITERAL VAR1 VAR2 VAR3 ...| SPLIT |VARFETCH 1 DIRECT TOLOAD|VARLOAD DIRECT Note: the DIRECT tells not to try to resolve compound symbols, this also means one must pass the variable names in uppercase (and stem suffixes in the exact case). -- Kris Buelens, IBM Belgium, VM customer support 2007/1/12, Peter Rothman [EMAIL PROTECTED]: We have an old REXX exec that I had to modify. This is a rather simplistic description but it consists of 2 parts - 1 to set up the environment(variables) and 2 to use the variables setup in 1. Bottom I had problems modifying it so I re-wrote it. The original used GLOBALV extensively - part 1 would do PUTs and part 2 would do GETs. Besides a lot of 'steam lining' I thought I would be 'clever' and changed the GLOBALVs to 'PIPE var VarName 1 | var VarName'. However the new exec ran much slower than the old. I then did a test to only compare GLOBALV PUT/GET to setting and retrieving the variable with PIPE var stage. The pipe stage was much slower. I thought the pipe logic would be better - obviously mistaken. Any comments - any other method I could have used that is perhaps faster than GLOBALV? Thanks Peter The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review retransmission dissemination or other use of or taking of any action in reliance upon this information by persons or entities other than the intended recipient or delegate is strictly prohibited. If you received this in error please contact the sender and delete the material from any computer. The integrity and security of this message cannot by guaranteed on the Internet. The Sender accepts no liability for the content of this e-mail or for the consequences of any actions taken on basis of the information provided. The recipient should check this e-mail and any attachments for the presence of viruses. The sender accepts no liability for any damage caused by any virus transmitted by this e-mail. This disclaimer is the property of the TTC and must not be altered or circumvented in any manner.
Re: Rexx performance question
Using a file to store the variables a while, uggghhh... File I/O remains terribly slow compared to memory access, even though you might save some CPU (I don't know if you will save) the result may be code than takes longer to complete in elapsed time. The fact that EXECIO is faster than PIPE to write files is that one often sees execs that every now and then write to a file. If you do that with PIPE, the file is closed after each write request; with EXECIO, the file is only closed when you explicitly ask for it. Again, the general rule is: do as much as possible in a single call, to PIPE, to XEDIt, to 2007/1/12, [EMAIL PROTECTED] [EMAIL PROTECTED]: From my testing, PIPES incur quite a bit of overhead when starting up. So, optimising means doing as much as possible within a PIPE to amortise that overhead over as much work as possible, and therefore using as few PIPE instances as possible. You could write the variables to a temporary disk file as well. But use EXECIO instead of PIPES to write the file, it uses less resources for small files. -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Peter Rothman Sent: January 12, 2007 10:55 To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Rexx performance question Tested that - also much slower than GLOBALV. Kris Buelens [EMAIL PROTECTED] il.com To Sent by: The IBM IBMVM@LISTSERV.UARK.EDU z/VM Operating cc System [EMAIL PROTECTED] Subject ARK.EDU Re: Rexx performance question 01/12/2007 10:23 AM Please respond to The IBM z/VM Operating System [EMAIL PROTECTED] ARK.EDU Have you tried this too? PIPE LITERAL VAR1 VAR2 VAR3 ...| SPLIT |VARFETCH 1 DIRECT TOLOAD|VARLOAD DIRECT Note: the DIRECT tells not to try to resolve compound symbols, this also means one must pass the variable names in uppercase (and stem suffixes in the exact case). -- Kris Buelens, IBM Belgium, VM customer support 2007/1/12, Peter Rothman [EMAIL PROTECTED]: We have an old REXX exec that I had to modify. This is a rather simplistic description but it consists of 2 parts - 1 to set up the environment(variables) and 2 to use the variables setup in 1. Bottom I had problems modifying it so I re-wrote it. The original used GLOBALV extensively - part 1 would do PUTs and part 2 would do GETs. Besides a lot of 'steam lining' I thought I would be 'clever' and changed the GLOBALVs to 'PIPE var VarName 1 | var VarName'. However the new exec ran much slower than the old. I then did a test to only compare GLOBALV PUT/GET to setting and retrieving the variable with PIPE var stage. The pipe stage was much slower. I thought the pipe logic would be better - obviously mistaken. Any comments - any other method I could have used that is perhaps faster than GLOBALV? Thanks Peter The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review retransmission dissemination or other use of or taking of any action in reliance upon this information by persons or entities other than the intended recipient or delegate is strictly prohibited. If you received this in error please contact the sender and delete the material from any computer. The integrity and security of this message cannot by guaranteed on the Internet. The Sender accepts no liability for the content of this e-mail or for the consequences of any actions taken on basis of the information provided. The recipient should check this e-mail and any attachments for the presence of viruses. The sender accepts no liability for any damage caused by any virus transmitted by this e-mail. This disclaimer is the property of the TTC and must not be altered or circumvented in any manner. -- Kris Buelens, IBM Belgium, VM customer support
Re: Rexx performance question
Why not define a vdisk for storing the variables? Definitely faster than the real thing. Steve G Kris Buelens [EMAIL PROTECTED] Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU 01/12/2007 11:38 AM Please respond to The IBM z/VM Operating System To: IBMVM@LISTSERV.UARK.EDU cc: Subject:Re: Rexx performance question Using a file to store the variables a while, uggghhh... File I/O remains terribly slow compared to memory access, even though you might save some CPU (I don't know if you will save) the result may be code than takes longer to complete in elapsed time. The fact that EXECIO is faster than PIPE to write files is that one often sees execs that every now and then write to a file. If you do that with PIPE, the file is closed after each write request; with EXECIO, the file is only closed when you explicitly ask for it. Again, the general rule is: do as much as possible in a single call, to PIPE, to XEDIt, to 2007/1/12, [EMAIL PROTECTED] [EMAIL PROTECTED]: From my testing, PIPES incur quite a bit of overhead when starting up. So, optimising means doing as much as possible within a PIPE to amortise that overhead over as much work as possible, and therefore using as few PIPE instances as possible. You could write the variables to a temporary disk file as well. But use EXECIO instead of PIPES to write the file, it uses less resources for small files. -Original Message- From: The IBM z/VM Operating System [mailto:IBMVM@LISTSERV.UARK.EDU ] On Behalf Of Peter Rothman Sent: January 12, 2007 10:55 To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Rexx performance question Tested that - also much slower than GLOBALV. Kris Buelens [EMAIL PROTECTED] il.com To Sent by: The IBM IBMVM@LISTSERV.UARK.EDU z/VM Operating cc System [EMAIL PROTECTED] Subject ARK.EDU Re: Rexx performance question 01/12/2007 10:23 AM Please respond to The IBM z/VM Operating System [EMAIL PROTECTED] ARK.EDU Have you tried this too? PIPE LITERAL VAR1 VAR2 VAR3 ...| SPLIT |VARFETCH 1 DIRECT TOLOAD|VARLOAD DIRECT Note: the DIRECT tells not to try to resolve compound symbols, this also means one must pass the variable names in uppercase (and stem suffixes in the exact case). -- Kris Buelens, IBM Belgium, VM customer support 2007/1/12, Peter Rothman [EMAIL PROTECTED]: We have an old REXX exec that I had to modify. This is a rather simplistic description but it consists of 2 parts - 1 to set up the environment(variables) and 2 to use the variables setup in 1. Bottom I had problems modifying it so I re-wrote it. The original used GLOBALV extensively - part 1 would do PUTs and part 2 would do GETs. Besides a lot of 'steam lining' I thought I would be 'clever' and changed the GLOBALVs to 'PIPE var VarName 1 | var VarName'. However the new exec ran much slower than the old. I then did a test to only compare GLOBALV PUT/GET to setting and retrieving the variable with PIPE var stage. The pipe stage was much slower. I thought the pipe logic would be better - obviously mistaken. Any comments - any other method I could have used that is perhaps faster than GLOBALV? Thanks Peter The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review retransmission dissemination or other use of or taking of any action in reliance upon this information by persons or entities other than the intended recipient or delegate is strictly prohibited. If you received this in error please contact the sender and delete the material from any computer. The integrity and security of this message cannot by guaranteed on the Internet. The Sender accepts no liability for the content of this e-mail or for the consequences of any actions taken on basis of the information provided. The recipient should check this e-mail and any attachments for the presence of viruses. The sender accepts no liability for any damage caused by any virus transmitted by this e-mail. This disclaimer is the property of the TTC and must not be altered or circumvented in any manner. -- Kris Buelens, IBM Belgium, VM customer support
Re: Rexx performance question
What is wrong with using GLOBALV? That can be memory-only as indicated in the original post (it specified GET and PUT, not GETS, GETP, PUTS or PUTP). There is no need to write to disk unless you need for the variables to be retained across IPLs or logons (SESSION or LASTING GLOBALV). Since it is strictly memory access, it ought to be faster than using either Pipe or EXECIO. However, it might be faster if the two EXECs could be joined together in a single EXEC so that the environment variables would already be there and not need to be passed to the EXEC that uses them. Regards, Richard Schuh From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Steve Gentry Sent: Friday, January 12, 2007 10:02 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Rexx performance question Why not define a vdisk for storing the variables? Definitely faster than the real thing. Steve G
Re: Rexx performance question
Even a VDISK means lots of overhead: one needs to go down all the way to CP. If variables are more/or less constant, one can store them in a CMS file, directly in a format understood by the VARLOAD stage. /varname/contents... Then one can EXECLOAD that file and code PIPE MYVARS FILE |VARLOAD DIRECT Note that you cannot code a filemode on the stage, the absence of a filemode tells PIPE to look for an EXECLOADed file first. 2007/1/12, Steve Gentry [EMAIL PROTECTED]: Why not define a vdisk for storing the variables? Definitely faster than the real thing. Steve G *Kris Buelens [EMAIL PROTECTED]* Sent by: The IBM z/VM Operating System IBMVM@LISTSERV.UARK.EDU 01/12/2007 11:38 AM Please respond to The IBM z/VM Operating System To:IBMVM@LISTSERV.UARK.EDU cc: Subject:Re: Rexx performance question Using a file to store the variables a while, uggghhh... File I/O remains terribly slow compared to memory access, even though you might save some CPU (I don't know if you will save) the result may be code than takes longer to complete in elapsed time. The fact that EXECIO is faster than PIPE to write files is that one often sees execs that every now and then write to a file. If you do that with PIPE, the file is closed after each write request; with EXECIO, the file is only closed when you explicitly ask for it. Again, the general rule is: do as much as possible in a single call, to PIPE, to XEDIt, to 2007/1/12, [EMAIL PROTECTED] [EMAIL PROTECTED] * [EMAIL PROTECTED][EMAIL PROTECTED] : From my testing, PIPES incur quite a bit of overhead when starting up. So, optimising means doing as much as possible within a PIPE to amortise that overhead over as much work as possible, and therefore using as few PIPE instances as possible. You could write the variables to a temporary disk file as well. But use EXECIO instead of PIPES to write the file, it uses less resources for small files. -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] *IBMVM@LISTSERV.UARK.EDU] On Behalf Of Peter Rothman Sent: January 12, 2007 10:55 To: [EMAIL PROTECTED] IBMVM@LISTSERV.UARK.EDU Subject: Re: Rexx performance question Tested that - also much slower than GLOBALV. Kris Buelens [EMAIL PROTECTED] *il.com* http://il.com/ To Sent by: The IBM [EMAIL PROTECTED]IBMVM@LISTSERV.UARK.EDU z/VM Operating cc System [EMAIL PROTECTED] * [EMAIL PROTECTED] Subject *ARK.EDU* http://ark.edu/ Re: Rexx performance question 01/12/2007 10:23 AM Please respond to The IBM z/VM Operating System [EMAIL PROTECTED] [EMAIL PROTECTED] *ARK.EDU* http://ark.edu/ Have you tried this too? PIPE LITERAL VAR1 VAR2 VAR3 ...| SPLIT |VARFETCH 1 DIRECT TOLOAD|VARLOAD DIRECT Note: the DIRECT tells not to try to resolve compound symbols, this also means one must pass the variable names in uppercase (and stem suffixes in the exact case). -- Kris Buelens, IBM Belgium, VM customer support 2007/1/12, Peter Rothman [EMAIL PROTECTED][EMAIL PROTECTED] : We have an old REXX exec that I had to modify. This is a rather simplistic description but it consists of 2 parts - 1 to set up the environment(variables) and 2 to use the variables setup in 1. Bottom I had problems modifying it so I re-wrote it. The original used GLOBALV extensively - part 1 would do PUTs and part 2 would do GETs. Besides a lot of 'steam lining' I thought I would be 'clever' and changed the GLOBALVs to 'PIPE var VarName 1 | var VarName'. However the new exec ran much slower than the old. I then did a test to only compare GLOBALV PUT/GET to setting and retrieving the variable with PIPE var stage. The pipe stage was much slower. I thought the pipe logic would be better - obviously mistaken. Any comments - any other method I could have used that is perhaps faster than GLOBALV? Thanks Peter The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review retransmission dissemination or other use of or taking of any action in reliance upon this information by persons or entities other than the intended recipient or delegate is strictly prohibited. If you received this in error please contact the sender and delete the material from any computer. The integrity and security of this message cannot by guaranteed on the Internet. The Sender accepts no liability for the content of this e-mail or for the consequences of any actions taken on basis of the information provided. The recipient should check this e-mail and any attachments for the presence of viruses. The sender accepts no liability for any damage caused by any virus transmitted by this e-mail
Re: Rexx performance question
We have not heard from Michael Coffin on this subject. IIRC he was very knowledgeable about using GLOBAL variables in REXX code. -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Schuh, Richard Sent: Friday, January 12, 2007 1:44 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Rexx performance question What is wrong with using GLOBALV? That can be memory-only as indicated in the original post (it specified GET and PUT, not GETS, GETP, PUTS or PUTP). There is no need to write to disk unless you need for the variables to be retained across IPLs or logons (SESSION or LASTING GLOBALV). Since it is strictly memory access, it ought to be faster than using either Pipe or EXECIO. However, it might be faster if the two EXECs could be joined together in a single EXEC so that the environment variables would already be there and not need to be passed to the EXEC that uses them. Regards, Richard Schuh _ From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Steve Gentry Sent: Friday, January 12, 2007 10:02 AM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: Rexx performance question Why not define a vdisk for storing the variables? Definitely faster than the real thing. Steve G If you are not an intended recipient of this e-mail, please notify the sender, delete it and do not read, act upon, print, disclose, copy, retain or redistribute it. Click here for important additional terms relating to this e-mail. http://www.ml.com/email_terms/
Re: Rexx performance question
I'd say there's nothing wrong with GLOBALV, but plumbers use their Piping tools. GLOBALV has an extra advantage: it is clear to the reader when one shares variables between execs. With a PIPE in a called exec one can do anything that the reader of the calling exec will not be aware off. Something more I remember: when REXX's VALUE function was extended to support GLOBAL variables, we were told that using VALUE() was faster than the GLOBLAV command. But, only when compared to GLOABLV with a single variable, so 'GLOBALV GET V1 V2 V3' outperforms 3 calls to VALUE(). -- Kris Buelens, IBM Belgium, VM customer support 2007/1/12, Stracka, James (GTI) [EMAIL PROTECTED]: We have not heard from Michael Coffin on this subject. IIRC he was very knowledgeable about using GLOBAL variables in REXX code. -Original Message- *From:* The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] *On Behalf Of *Schuh, Richard *Sent:* Friday, January 12, 2007 1:44 PM *To:* IBMVM@LISTSERV.UARK.EDU *Subject:* Re: Rexx performance question What is wrong with using GLOBALV? That can be memory-only as indicated in the original post (it specified GET and PUT, not GETS, GETP, PUTS or PUTP). There is no need to write to disk unless you need for the variables to be retained across IPLs or logons (SESSION or LASTING GLOBALV). Since it is strictly memory access, it ought to be faster than using either Pipe or EXECIO. However, it might be faster if the two EXECs could be joined together in a single EXEC so that the environment variables would already be there and not need to be passed to the EXEC that uses them. Regards, Richard Schuh
performance question
Title: performance question Good morning everyone. I have a little performance question to pose this morning. This is sort of related to the thread 'VTAM Cross Domain problem/question'. We have an application that 'webifies' the look of some CICS screens. The app runs on a wintell server somewhere that connects the session via TCP/IP to the Z/890. My VM-TCPIP uses the SCEXIT (REXX not assembler) to DAIL to a VSE/VTAM. After every CICS transaction the session gets DROPPED. When looking at my log I see ten's of thousands of DIAL/DROPPED messages per day. Here is the question: From the z/VM standpoint how bad is this? Where (in either VMPERFTK or ESAMON) can I find stats to backup my assumption that this is not good? Thanks Tom __ ella for Spam Control has removed VSE-List messages and set aside VM-List for me You can use it too - and it's FREE! http://www.ellaforspam.com
Re: performance question
Huegel, Thomas [EMAIL PROTECTED] writes: Tom, I'm not sure I completely follow the question. I am not aware of any way to get just the cost of the SCEXIT from existing data. You could at least bound it by looking at total costs in the TCP/IP stack machine to understand what the costs may be. One thought is to add something to the exit that grabs perhaps QUERY TIME or something before at entering and leaving the exit. Bill Bitner - VM Performance Evaluation - IBM Endicott - 607-429-3286
Re: performance question
Title: RE: performance question Bill, I wasn't concerned with just the SCEXIT itself, if I thought that was the issue I would rewrite it in assembler. I was interested in the whole DIAL/DROP path. From the time TCP/IP first saw the connection until VSE/VTAM saw the terminal and how much overhead there was to keep dialing and dropping the same terminal. Then my next step will be to try and find what goes on in VSE with VTAM, CICS autoinstalls, lostterm clean ups ... Tom -Original Message- From: The IBM z/VM Operating System [mailto:IBMVM@LISTSERV.UARK.EDU]On Behalf Of Bill Bitner Sent: Thursday, October 12, 2006 3:31 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: performance question Huegel, Thomas [EMAIL PROTECTED] writes: Tom, I'm not sure I completely follow the question. I am not aware of any way to get just the cost of the SCEXIT from existing data. You could at least bound it by looking at total costs in the TCP/IP stack machine to understand what the costs may be. One thought is to add something to the exit that grabs perhaps QUERY TIME or something before at entering and leaving the exit. Bill Bitner - VM Performance Evaluation - IBM Endicott - 607-429-3286 __ ella for Spam Control has removed VSE-List messages and set aside VM-List for me You can use it too - and it's FREE! http://www.ellaforspam.com
Re: performance question
Huegel, Thomas [EMAIL PROTECTED] writes: Thank you, I better understand your problem. There is no trivial way I know of to break this apart as you would like. My best suggestion is: - isolate this processing to a TCP/IP stack that does this alone - use either SCEXIT or cons logs to track rate of dial/drop. - record total usage of the TCP/IP stack from Performance Toolkit - correlate the CPU to dial/drop rate to get an average cost of cost in the TCP/IP stack - you could also perhaps create a dummy guest for test purposes and measure that part of it without skewing from other work. Ugly, but all I have to offer. And would give you ballpark numbers. Not sure you need any significant precision. Bill Bitner - VM Performance Evaluation - IBM Endicott - 607-429-3286
Re: performance question
Title: performance question Tom, although I couldn't open the stuff you tried to provide in your append, the data you sent me by separate mail gave me the required information to tell what's wrong: - Your RESET specifications are fine. This isevidenced by the report headers From 2006/04/25 00:14:00 To 2006/04/26 00:00:00 For 85560 Secs 23:46:00 i.e. you really get averages for the whole day, as expected. (I assume that the late start time in the example was due to PerfKit being activated only at 00:14.) - I assume that when you wrote '.. all my reports start at 12:01:00..' you referred to the 'by time' logs you printed. Their headers tell you that the averages shown are also for the whole day, so they're based on the correct reset time, but the detail lines start only with the sample periodending at 12:01. This is working as designed: What you see is the effect of a documented restriction that only allows PerfKit to hold a maximum of 720detail lines in its 'by time' log buffers, so when the chosen granularity for the logs is 1 minute you'll only see the detail lines for the last 12 hours (see description of the 'FC MONCOLL REDISP' command). To see detail lines for the whole 24 hours change the 'by time' interval to 2 minutes (FC SET BYTIME 2), or to any other higher value. If you always want to print logs for the whole day then I'd suggest to set the BYTIME interval to 10 or 15 minutes. That way the output size is reduced to something more easily manageable. Eginhard Jaeger - Original Message - From: Huegel, Thomas To: IBMVM@LISTSERV.UARK.EDU Sent: Wednesday, April 26, 2006 3:42 PM Subject: Re: performance question I tried this in my $profile.. I get this display. My report heading looks like this. BUT my reports still start at 12:00:00 and end at 23:59:00.. Any ideas what I may have wrong??? Thank you. Tom -Original Message-From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED]On Behalf Of Eginhard JaegerSent: Monday, April 24, 2006 9:05 AMTo: IBMVM@LISTSERV.UARK.EDUSubject: Re: performance question Can anybody tell me how to get reports from PERFKIT that start at 00:01:00 and go to 23:59:00 ? I have tried everything I can find and all my reports start at 12:01:00 and end at 23:59:00. What am I missing? The times when counters should be reset in PerfKit are defined by arguments of the command 'FC MONCOLL RESET ...'. Entering the command without further arguments will tell you what your current settings are, and my guess is you have defined a reset at noon. Note that each automated 'print' request (i.e. P-suffix after the time) will automatically reset the corresponding counters, i.e. it will become the start of a new reporting period unless it is superseded by a later explicit 'hh:mm:ssR_P' reset specification. For automatic resetting at 00:01 and printing of reports at 23:59 you'd need just the statement 'FC MONCOLL RESET 00:01:00R_P 23:59:00P' Eginhard Jaeger ella for Spam Control has removed 3853 VSE-List messages and set aside 2172 VM-List for meYou can use it too - and it's FREE!www.ellaforspam.com
Re: performance question
Title: performance question I tried this in my $profile.. I get this display. My report heading looks like this. BUT my reports still start at 12:00:00 and end at 23:59:00.. Any ideas what I may have wrong??? Thank you. Tom -Original Message-From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED]On Behalf Of Eginhard JaegerSent: Monday, April 24, 2006 9:05 AMTo: IBMVM@LISTSERV.UARK.EDUSubject: Re: performance question Can anybody tell me how to get reports from PERFKIT that start at 00:01:00 and go to 23:59:00 ? I have tried everything I can find and all my reports start at 12:01:00 and end at 23:59:00. What am I missing? The times when counters should be reset in PerfKit are defined by arguments of the command 'FC MONCOLL RESET ...'. Entering the command without further arguments will tell you what your current settings are, and my guess is you have defined a reset at noon. Note that each automated 'print' request (i.e. P-suffix after the time) will automatically reset the corresponding counters, i.e. it will become the start of a new reporting period unless it is superseded by a later explicit 'hh:mm:ssR_P' reset specification. For automatic resetting at 00:01 and printing of reports at 23:59 you'd need just the statement 'FC MONCOLL RESET 00:01:00R_P 23:59:00P' Eginhard Jaeger ella for Spam Control has removed 3853 VSE-List messages and set aside 2172 VM-List for meYou can use it too - and it's FREE!www.ellaforspam.com
Re: performance question
Title: performance question Can anybody tell me how to get reports from PERFKIT that start at 00:01:00 and go to 23:59:00 ? I have tried everything I can find and all my reports start at 12:01:00 and end at 23:59:00. What am I missing? The times when counters should be reset in PerfKit are defined by arguments of the command 'FC MONCOLL RESET ...'. Entering the command without further arguments will tell you what your current settings are, and my guess is you have defined a reset at noon. Note that each automated 'print' request (i.e. P-suffix after the time) will automatically reset the corresponding counters, i.e. it will become the start of a new reporting period unless it is superseded by a later explicit 'hh:mm:ssR_P' reset specification. For automatic resetting at 00:01 and printing of reports at 23:59 you'd need just the statement 'FC MONCOLL RESET 00:01:00R_P 23:59:00P' Eginhard Jaeger
performance question
Title: performance question Can anybody tell me how to get reports from PERFKIT that start at 00:01:00 and go to 23:59:00 ? I have tried everything I can find and all my reports start at 12:01:00 and end at 23:59:00. What am I missing? Thanks __ ella for Spam Control has removed VSE-List messages and set aside VM-List for me You can use it too - and it's FREE! http://www.ellaforspam.com
Re: VM Performance Question
You got me. I keep forgetting that the 2 GB I/O boundry in z/VM 5.1 and below isn't the same as executing code. Neither of these, have ever bitten me. The VM folks have been very good about keeping ahead of the curve, as far as I have been concerned. Tom Duerbusch THD Consulting Dennis.L.O'[EMAIL PROTECTED] 3/17/2006 1:01 PM Correction to item 1: z/VM 5.1 and below can support more than 2G of central storage in the LPAR, as long as you're on zSeries hardware. They just have to move pages below 2G when CP needs to do something with them, such as I/O. Dennis Do you think it's a good idea, letting an Arab country take over our ports? This is like letting Bill Clinton be the manager of a Hooters. -- Jay Leno -Original Message- From: The IBM z/VM Operating System [mailto:[EMAIL PROTECTED] On Behalf Of Tom Duerbusch Sent: Friday, March 17, 2006 09:19 To: IBMVM@LISTSERV.UARK.EDU Subject: Re: VM Performance Question I don't know for sure if it really helps, but I have been saying the same thing for years. Setting expanded storage is a good thing for an actively paging system. Also by reducing the amount of central storage, would cause increased paging. But if you are not actively paging, why have expanded storage. But this is only good for: 1. If you are on z/VM 5.1 or under and have 2 GB or less in the LPAR. If you have more than 2 GB, then you have to configure expanded storage to use the rest, so it is a moot point. 2. You are not actively paging. IMHO, a few pages a second or a spike when something relatively rare happens (a new guest being IPL'ed), CICS being cycled, xedit a million line printout, etc. But when you start actively paging, then, for performance reasons, you do need to start configuring expanded storage. I have no proof, but I doubt that you will see any difference (a performance monitor will), unless you are paging a lot. I always question rules of thumb and other performance tidbits. What conditions do these solve, and am I even close to one of those conditions. There are many things that really only for large or heavy use, shops. Tom Duerbusch THD Consulting [EMAIL PROTECTED] 3/15/2006 4:21 PM The link below is a VM Performance article with the ending Bottom Lines recommendations. Has anyone done this and did it in fact improve performance? Bottom Lines |--- ---| | | |For VM/ESA, if you have plenty of storage, little paging, a well tuned MDC, a | |consistent load, and a robust DASD paging configuration, then all real storage| |is most likely the best case. Otherwise, consider configuring some storage as | | expanded storage. A ballpark starting point is 25% of processor storage. You | |must configure anything above 2GB as expanded storage. | |--- ---| |--- ---| | | | For z/VM, you should still configure some storage as expanded. The 25% value | |may still be a good starting point. Most systems do not need more than 2GB of | | expanded storage regardless of the total storage available. Systems with no | | constraint below 2GB, can use less expanded storage. Constraint below 2GB | | often is indicated by significant paging to DASD and a large number of pages | |available above 2GB (as seen by QUERY FRAMES command or your favorite | | performance tool). In that case, you will want to add more expanded storage. | | You may also be able to free-up expanded storage by limiting the amount of | | expanded storage in use by minidisk cache (MDC) via the CP command SET MDC | | XSTORE or with a system configuration statement. | |--- ---| www.vm.ibm.com/perf/tips/storconf.html TIA Jan Canavan